Multimodal imaging measures in the prediction of clinical response to deep brain stimulation for refractory depression: A machine learning approach

Abstract

Objectives

This study compared machine learning models using unimodal imaging measures and combined multi-modal imaging measures for deep brain stimulation (DBS) outcome prediction in treatment resistant depression (TRD).

Methods

Regional brain glucose metabolism (CMRGlu), cerebral blood flow (CBF), and grey matter volume (GMV) were measured at baseline using 18F-fluorodeoxy glucose (18F-FDG) positron emission tomography (PET), arterial spin labelling (ASL) magnetic resonance imaging (MRI), and T1-weighted MRI, respectively, in 19 patients with TRD receiving subcallosal cingulate (SCC)-DBS. Responders (n = 9) were defined by a 50% reduction in HAMD-17 at 6 months from the baseline. Using an atlas-based approach, values of each measure were determined for pre-selected brain regions. OneR feature selection algorithm and the naïve Bayes model was used for classification. Leave-out-one cross validation was used for classifier evaluation.

Results

The performance accuracy of the CMRGlu classification model (84%) was greater than CBF (74%) or GMV (74%) models. The classification model using the three image modalities together led to a similar accuracy (84%0 compared to the CMRGlu classification model.

Conclusions

CMRGlu imaging measures may be useful for the development of multivariate prediction models for SCC-DBS studies for TRD. The future of multivariate methods for multimodal imaging may rest on the selection of complementing features and the developing better models.Clinical Trial Registration: ClinicalTrials.gov (#NCT 01983904)

Keywords:

• subgenual cingulate
• deep brain stimulation
• treatment resistant depression
• brain imaging
• machine learning

Acknowledgments

Partial data were presented as a poster at the 74^th Society of Biological Psychiatry annual meeting in May 2019. We thank Maida Khan RN for providing assistance to prepare tables and figures in the manuscript.

Authors contributions

RR and ZK designed the main SCC-DBS clinical trial. RR designed this study, collected clinical data, planned the analysis, interpreted the results, and wrote the manuscript. EB and DL collected PET, CBV and GMV imaging data and performed univariate analysis. PM, JAM, and NF performed the machine learning analysis. ZK implanted the DBS system. CM contributed to PET scanning and PET data collection. All authors contributed to the interpretation of the data, critical review of the paper and approved the final manuscript.

Statement of interest

Dr. Ramasubbu has received an honorarium for serving in the advisory committee of Astra Zeneca, Lund beck, Janssen, and Otsuka. He also received an investigator-initiated grant from Astra Zeneca and Pfizer. Other authors report there are no competing interests to declare.

Data availability statement

The datasets used in the study are available from the corresponding author upon reasonable request.

Additional information

Funding

Funding for the study was provided by a grant from Alberta Innovates Health Solutions (AIHS), Alberta, Canada. The funding agency had no role in the study design, collection, analysis and interpretation of data, and preparation, review, or approval of the manuscript.